Skip to main content

RSS feed parser server for Model Context Protocol (MCP)

Project description

MCP RSS Feed Server

This project is a server implementation that detects and parses RSS/Atom feeds using the Model Context Protocol (MCP).

Available Tools

feed

Detects and parses RSS/Atom feeds from a given URL.

  • url (string, required): Target URL to analyze for feeds
  • limit (integer, optional): Maximum number of entries to return (default: 10, max: 100)

Returns: JSON containing:

  • feed_info: Feed metadata (title, description, language, etc.)
  • entries: Array of feed entries with title, link, published date, description, author, and GUID
  • metadata: Response metadata including feed URL, entry counts, and status

Features

  • Automatic Feed Detection: Discovers RSS/Atom feeds from websites automatically
  • Multiple Feed Format Support: Handles RSS 2.0, RSS 1.0, Atom 1.0, and other formats
  • Intelligent Parsing: Extracts clean, structured data from feeds
  • HTML Cleanup: Removes HTML tags from descriptions for clean text output
  • Fallback Mechanisms: Tries common feed paths when direct detection fails
  • Error Handling: Robust error handling with detailed logging

Installation

Using uv (recommended)

No special installation is needed when using uv. You can run mcp-server-rss directly with uvx.

Using PIP

Alternatively, you can install mcp-server-rss using pip:

pip install mcp-server-rss

After installation, you can run it as a script like this:

mcp-server-rss

Configuration

Configure for Claude.app

Add to your Claude settings:

Using uvx
{
  "mcpServers": {
    "rss": {
      "command": "uvx",
      "args": ["mcp-server-rss"]
    }
  }
}
Using pip installation
{
  "mcpServers": {
    "rss": {
      "command": "mcp-server-rss"
    }
  }
}

Configure for VS Code

For quick installation, use one of the one-click install buttons below...

Install with UV in VS Code

Command Line Options

You can specify the following options when running the server:

You can specify the following options when running the server:

  • --sse: Enable Server-Sent Events transport (on/off)
  • --host: Server bind address (default: localhost)
  • --port: Server port number (default: 8000)
  • --log-level: Logging verbosity (debug, info, warning, error)

License

MIT License - see LICENSE file for details.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

mcp_server_rss-0.1.0.tar.gz (43.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

mcp_server_rss-0.1.0-py3-none-any.whl (9.4 kB view details)

Uploaded Python 3

File details

Details for the file mcp_server_rss-0.1.0.tar.gz.

File metadata

  • Download URL: mcp_server_rss-0.1.0.tar.gz
  • Upload date:
  • Size: 43.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: python-httpx/0.28.1

File hashes

Hashes for mcp_server_rss-0.1.0.tar.gz
Algorithm Hash digest
SHA256 46840ede47188bed8e55a8a362d1588184fdf2c77c45a05592e4950e94363ff0
MD5 2fab225712b23c9b1fe5faebfde0db5c
BLAKE2b-256 6d37100d6e6b910fcc192d6ed520d9a46b0a4c27a0920267784e89d1f351ed9a

See more details on using hashes here.

File details

Details for the file mcp_server_rss-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for mcp_server_rss-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 b7bcd77e8cb903505e584bf7dc6c18cb9a8f840c6487c8d0836fd8657e9b405e
MD5 758b6019d6fda06adbfb62ef36ad0388
BLAKE2b-256 0ba8c47c974a1d7572f844f9c0ddccf7489867a67427d7750cb3215d3c4d363f

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page